Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their context within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows periods and starts new sentences

    np_acts-logits-general · gemini-2.0-flash

    interfaith children and marriage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -1.25
     Jefus
    -1.21
     Shakspeare
    -1.20
     Anſ
    -1.18
     Efq
    -1.17
     himſelf
    -1.16
     itſelf
    -1.16
     myſelf
    -1.15
     Eſ
    -1.14
     Monfieur
    -1.12
    POSITIVE LOGITS
     we
    1.28
     there
    1.15
     it
    1.14
     if
    1.11
     they
    1.10
     no
    1.06
     this
    1.04
     the
    1.04
     he
    1.00
     but
    1.00
    Act Density 0.411%

    No Known Activations